Identifying vulnerable older adult populations by contextualizing geriatric syndrome information in clinical notes of electronic health records

OBJECTIVE Geriatric syndromes such as functional disability and lack of social support are often not encoded in electronic health records (EHRs), thus obscuring the identification of vulnerable older adults in need of additional medical and social services. In this study, we automatically identify vulnerable older adult patients with geriatric syndrome based on clinical notes extracted from an EHR system, and demonstrate how contextual information can improve the process. MATERIALS AND METHODS We propose a novel end-to-end neural architecture to identify sentences that contain geriatric syndromes. Our model learns a representation of the sentence and augments it with contextual information: surrounding sentences, the entire clinical document, and the diagnosis codes associated with the document. We trained our system on annotated notes from 85 patients, tuned the model on another 50 patients, and evaluated its performance on the rest, 50 patients. RESULTS Contextual information improved classification, with the most effective context coming from the surrounding sentences. At sentence level, our best performing model achieved a micro-F1 of 0.605, significantly outperforming context-free baselines. At patient level, our best model achieved a micro-F1 of 0.843. DISCUSSION Our solution can be used to expand the identification of vulnerable older adults with geriatric syndromes. Since functional and social factors are often not captured by diagnosis codes in EHRs, the automatic identification of the geriatric syndrome can reduce disparities by ensuring consistent care across the older adult population. CONCLUSION EHR free-text can be used to identify vulnerable older adults with a range of geriatric syndromes.

[1]  Sunghwan Sohn,et al.  Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications , 2010, J. Am. Medical Informatics Assoc..

[2]  Hadi Kharrazi,et al.  Assessing markers from ambulatory laboratory tests for predicting high-risk patients. , 2018, The American journal of managed care.

[3]  M. Gulliford,et al.  Differences in Health at Age 100 According to Sex: Population‐Based Cohort Study of Centenarians Using Electronic Health Records , 2015, Journal of the American Geriatrics Society.

[4]  Rachel Gold,et al.  "Community vital signs": incorporating geocoded social determinants into electronic records to promote patient and population health , 2016, J. Am. Medical Informatics Assoc..

[5]  Eric W Ford,et al.  Assessing electronic health record implementation challenges using item response theory. , 2016, The American journal of managed care.

[6]  Hadi Kharrazi,et al.  Evaluating the Impact of Prescription Fill Rates on Risk Stratification Model Performance , 2017, Medical care.

[7]  Son Doan,et al.  Application of information technology: MedEx: a medication information extraction system for clinical narratives , 2010, J. Am. Medical Informatics Assoc..

[8]  Mark Dredze,et al.  Extraction of Geriatric Syndromes From Electronic Health Record Clinical Notes: Assessment of Statistical Natural Language Processing Methods , 2018, JMIR medical informatics.

[9]  Hadi Kharrazi,et al.  Comparing Population-based Risk-stratification Model Performance Using Demographic, Diagnosis and Medication Data Extracted From Outpatient Electronic Health Records Versus Administrative Claims , 2017, Medical care.

[10]  Hadi Kharrazi,et al.  The Impact of Social Determinants of Health on Hospitalization in the Veterans Health Administration. , 2019, American journal of preventive medicine.

[11]  Parisa Rashidi,et al.  Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis , 2017, IEEE Journal of Biomedical and Health Informatics.

[12]  Hadi Kharrazi,et al.  Assessing the Impact of Body Mass Index Information on the Performance of Risk Adjustment Models in Predicting Health Care Costs and Utilization , 2018, Medical care.

[13]  Michael N Cantor,et al.  Integrating Data On Social Determinants Of Health Into Electronic Health Records. , 2018, Health affairs.

[14]  Robert L Phillips,et al.  Community Vital Signs: Taking the Pulse of the Community While Caring for Patients , 2016, The Journal of the American Board of Family Medicine.

[15]  Julia Adler-Milstein,et al.  Electronic Health Record Adoption In US Hospitals: Progress Continues, But Challenges Persist. , 2015, Health affairs.

[16]  Claire Cardie,et al.  Annotating Expressions of Opinions and Emotions in Language , 2005, Lang. Resour. Evaluation.

[17]  Hadi Kharrazi,et al.  Forecasting the Maturation of Electronic Health Record Functions Among US Hospitals: Retrospective Analysis and Predictive Model , 2018, Journal of medical Internet research.

[18]  C Weijer,et al.  When is a randomised controlled trial health equity relevant? Development and validation of a conceptual framework , 2017, BMJ Open.

[19]  Thomas G. Dietterich Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[20]  Elham Hatef,et al.  A Population Health Measurement Framework: Evidence-Based Metrics for Assessing Community-Level Population Health in the Global Budget Context. , 2018, Population health management.

[21]  John W. Loonsk,et al.  A proposed national research and development agenda for population health informatics: summary recommendations from a national expert workshop , 2017, J. Am. Medical Informatics Assoc..

[22]  Stephanie Studenski,et al.  Geriatric Syndromes: Clinical, Research, and Policy Implications of a Core Geriatric Concept , 2007, Journal of the American Geriatrics Society.

[23]  Hadi Kharrazi,et al.  Public and Population Health Informatics: The Bridging of Big Data to Benefit Communities , 2018, Yearbook of Medical Informatics.

[24]  M. O. Olde Rikkert,et al.  Geriatric syndromes: medical misnomer or progress in geriatrics? , 2003, The Netherlands journal of medicine.

[25]  Hadi Kharrazi,et al.  A Practical Comparison Between the Predictive Power of Population-based Risk Stratification Models Using Data From Electronic Health Records Versus Administrative Claims: Setting a Baseline for Future EHR-derived Risk Stratification Models. , 2018, Medical care.

[26]  Ritu Sadana,et al.  Healthy Ageing: Raising Awareness of Inequalities, Determinants, and What Could Be Done to Improve Health Equity. , 2016, The Gerontologist.

[27]  Spyros Kotoulas,et al.  Medical Text Classification using Convolutional Neural Networks , 2017, Studies in health technology and informatics.

[28]  Hadi Kharrazi,et al.  Comparing clinician descriptions of frailty and geriatric syndromes using electronic health records: a retrospective cohort study , 2017, BMC Geriatrics.

[29]  Hadi Kharrazi,et al.  A public health perspective on using electronic health records to address social determinants of health: The potential for a national system of local community health records in the United States , 2019, Int. J. Medical Informatics.

[30]  Hadi Kharrazi,et al.  A State-wide Health IT Infrastructure for Population Health: Building a Community-wide Electronic Platform for Maryland’s All-Payer Global Budget , 2017, Online journal of public health informatics.

[31]  Peter Tugwell,et al.  CONSORT-Equity 2017 extension and elaboration for better reporting of health equity in randomised trials , 2017, British Medical Journal.

[32]  Erik Cambria,et al.  Recent Trends in Deep Learning Based Natural Language Processing , 2017, IEEE Comput. Intell. Mag..

[33]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[34]  Hadi Kharrazi,et al.  The Value of Unstructured Electronic Health Record Data in Geriatric Syndrome Case Identification , 2018, Journal of the American Geriatrics Society.

[35]  Hadi Kharrazi,et al.  Defining and Assessing Geriatric Risk Factors and Associated Health Care Utilization Among Older Adults Using Claims and Electronic Health Records , 2018, Medical care.

[36]  Q. Mcnemar Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[37]  Hadi Kharrazi,et al.  Prospective EHR-Based Clinical Trials: The Challenge of Missing Data , 2014, Journal of General Internal Medicine.

[38]  Barbara McLaughlin,et al.  Fostering geriatrics in associate degree nursing education: an assessment of current curricula and clinical experiences. , 2010, The Journal of nursing education.

[39]  Shaun J. Grannis,et al.  Using structured and unstructured data to identify patients' need for services that address the social determinants of health , 2017, Int. J. Medical Informatics.